Re: [OMPI devel] [OMPI svn] svn:open-mpi r24251

2011-01-14 Thread Mohamad Chaarawi
-1372,6 +1374,7 @@ > */ > if( ORTE_SUCCESS != (ret = > orte_errmgr_base_restart_job(current_global_jobid, global_handle, seq_num) ) > ) { > ORTE_ERROR_LOG(ret); > +orte_snapc_ckpt_state_notify(ORTE_SNAPC_CKPT_STATE_NO_RESTART

[OMPI devel] btl_openib_exclusivity

2007-06-05 Thread Mohamad Chaarawi
I was going through the MCA btl parameters for openib and came across this parameter in which i didn't get what it actually does: MCA btl: parameter "btl_openib_exclusivity" (current value: "1024") BTL exclusivity (must be >= 0) anybody

Re: [OMPI devel] [RFC] Sparse group implementation

2007-07-25 Thread Mohamad Chaarawi
r turns off >> sparse groups, or >> b) there's an added check in the inline function for whether the MCA >> parameter is on >> >> I'm personally in favor of a) because it means only one conditional >> in the critical path. > > I don't really c

Re: [OMPI devel] [RFC] Sparse group implementation

2007-07-25 Thread Mohamad Chaarawi
Sorry the additional parameters are 5 integers and 3 pointers.. Mohamad On Wed, July 25, 2007 9:45 pm, Mohamad Chaarawi wrote: > In the current code, almost all #ifs are due to the fact that we don't > want to add the extra memory by the sparse parameters that are added to > the g

Re: [OMPI devel] [RFC] Sparse group implementation

2007-07-26 Thread Mohamad Chaarawi
ode, which im for.. > > Other than that, I think you've got my concerns pretty much addressed. > > Brian > > On Jul 25, 2007, at 8:45 PM, Mohamad Chaarawi wrote: > >> In the current code, almost all #ifs are due to the fact that we don't >> want to a

Re: [OMPI devel] [RFC] Sparse group implementation

2007-07-26 Thread Mohamad Chaarawi
On Thu, July 26, 2007 1:18 pm, Brian Barrett wrote: > On Jul 26, 2007, at 12:00 PM, Mohamad Chaarawi wrote: > >>> 2) I think it would be better to always have the flags and macros >>> available (like OMPI_GROUP_SPORADIC and OMPI_GROUP_IS_SPORADIC) even >>> when

Re: [OMPI devel] [RFC] Sparse group implementation

2007-07-26 Thread Mohamad Chaarawi
On Thu, July 26, 2007 2:07 pm, Brian Barrett wrote: > On Jul 26, 2007, at 1:01 PM, Mohamad Chaarawi wrote: > >> >> On Thu, July 26, 2007 1:18 pm, Brian Barrett wrote: >>> On Jul 26, 2007, at 12:00 PM, Mohamad Chaarawi wrote: >>> >>>>> 2) I th

[OMPI devel] FW: [RFC] Sparse group implementation]

2007-07-27 Thread Mohamad Chaarawi
al. > Another proposition that i mentioned before is to keep the sparse parameters in the group structure (not compile them out) when the sparse groups are disabled, which will remove almost all #ifs from the code, which will be much easier for the eyes (the main reason).. Brian had some object

[OMPI devel] Sparse Branch (Heads up Commit)

2007-08-02 Thread Mohamad Chaarawi
need to add a line to ompi_info to indicate wether the sparse groups are indicated in the build or not. I will most probably commit tomorrow afternoon or sometime in the weekend, Unless someone objects.. Thank you, -- Mohamad Chaarawi Instructional Assistant http://www.cs.uh.edu

Re: [OMPI devel] Problem with group code

2007-08-16 Thread Mohamad Chaarawi
proc_count) { > +if (peer_id >= group->grp_proc_count || peer_id < 0) { > opal_output(0, "ompi_group_lookup_peer: invalid peer index > (%d)", peer_id); > >> Thanks, >> >> Tim >> ___ >>

Re: [OMPI devel] Problem with group code

2007-08-16 Thread Mohamad Chaarawi
e time. > > But if you apply the patch I sent, it will tell you when an invaild > lookup happens, which should be every time it runs. > > Tim > > Mohamad Chaarawi wrote: >> Hey Tim, >> >> I understand what you are talking about. >> Im trying to reproduce t